Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?

[2505.24778] Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty? Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2505.24778 (cs) [Submitted on 30 May 2025 ( v1 ), last revised 11 Apr 2026 (this version, v3)] Title: Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty? Authors: Jiayu Liu , Qing Zong , Weiqi Wang , Yangqiu Song View a PDF of the paper titled Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?, by Jiayu Liu and 3 other authors View PDF HTML (experimental) Abstract: As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically express confidence through epistemic markers (e.g., "fairly confident") instead of numerical values. However, it remains unclear whether LLMs consistently use these markers to reflect their intrinsic confidence due to the difficulty of quantifying uncertainty associated with various markers. To address this gap, we first define marker confidence as the observed accuracy when a model employs an epistemic marker. We evaluate its stability across multiple question-answering datasets in both in-distribution and out-of-distribution settings for open-source and proprietary LLMs. Our results show that while markers generalize well within the same distribution, their confidence is inconsistent in out-of-distribution scenarios. These findings raise significant concerns about the reliability of epistemic markers for confidence estimation, underscoring the need for improved alignment between marker based confidence and actual model uncertainty. Our code is available at this https URL . Comments: ACL 2025 Main Subjects: Computation and Language (cs.CL) Cite as: arXiv:2505.24778 [cs.CL] (or arXiv:2505.24778v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2505.24778 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jiayu Liu [ view email ] [v1] Fri, 30 May 2025 16:41:24 UTC (433 KB) [v2] Tue, 1 Jul 2025 05:53:22 UTC (433 KB) [v3] Sat, 11 Apr 2026 00:47:37 UTC (423 KB) Full-text links: Access Paper: View a PDF of the paper titled Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?, by Jiayu Liu and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2025-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey#479897
• Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact#290636
• Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models#1118582
• Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models#1062665
• Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models#1028739